Samsung will handle IBM Telum II AI semiconductor production

Samsung Foundry will handle the production of new IBM AI semiconductor products. The company has officially launched the Telum II processor and Spyre AI accelerator. These chips will enhance performance and efficiency in IBM Z and LinuxOne.

IBM will integrate the Telum II processor and Spyre AI accelerator in its large-scale mainframe computers. The mass production of these IBM AI semiconductor chips will be handled by Samsung Foundry using its advanced 5nm process.

Telum II

IBM’s latest addition to its Telum series offers a 40% increase in cache compared to its predecessor. It integrates an AI accelerator and includes a data processing unit (DPU), making it a powerful tool for handling complex computing tasks.

Spyre AI accelerator

The company’s new Spyre AI accelerator specializes in complex AI models and generative AI inference. It promises memory expansion capabilities of up to 1TB and is designed to consume no more than 75W power per card.

Samsung Foundry’s 5nm process will produce these semiconductors. It will ensure that IBM’s new products are both advanced and efficient. However, these chipsets are not directly competing with Nvidia which has been a dominant player.

IBM x Samsung

Developed using Samsung 5nm technology, the new IBM Telum II processor will feature eight high-performance cores running at 5.5GHz. Telum II will include a 40% increase in on-chip cache capacity, with the virtual L3 and virtual L4 growing to 360MB and 2.88GB respectively.

The processor integrates a new data processing unit (DPU) specialized for IO acceleration and the next generation of on-chip AI acceleration. These hardware enhancements are designed to provide significant performance improvements for clients over previous generations.